Scholar
Gabriele Sarti
Google Scholar ID: sK0B_08AAAAJ
PhD Student, University of Groningen
Citations & Impact
Citations
745
H-index
12
i10-index
16
Publications
20
Co-authors
19
list available
Publications
Cited
0
Resume (English only)
Academic Achievements
- - Publications: 'QE4PE: Word-level Quality Estimation for Human Post-Editing' accepted by TACL, 'Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement' accepted to EMNLP Main
- - Co-organizing BlackboxNLP Workshop 2025
- - 'Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation' accepted to EMNLP 2024, 'Multi-property Steering of Large Language Models with Dynamic Activation Composition' accepted to BlackboxNLP 2024
- - 'PECoRe' accepted to ICLR 2024, presented in Vienna
- - Development of open-source interpretability software projects for reproducible analysis of model behaviors
Research Experience
- - Applied Scientist Intern: Amazon Web Services (US), 2022
- - Research Scientist: Aindo (IT), 2020 - 2021
- - Visiting Research Assistant: ILC-CNR ItaliaNLP Lab (IT), 2019
Education
- - PhD in Natural Language Processing, University of Groningen (NL), 2021 - Ongoing, Supervisors: Arianna Bisazza, Malvina Nissim, Grzegorz Chrupała
- - MSc. in Data Science and Scientific Computing, University of Trieste & SISSA (IT), 2018 - 2020
- - DEC in Software Management, Cégep de Saint-Hyacinthe (CA), 2015 - 2018
Background
- Research Interests: Generative Language Models, Deep Learning Interpretability, Human-AI Interaction, User Modeling and Personalization. Background: He is a PhD student in the Natural Language Processing group at the University of Groningen and a member of the InDeep consortium, working on user-centric interpretability for generative language models.
Miscellany
- Anonymous constructive feedback is always welcome! 🙂
